Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks
For practitioners deploying DNNs in untrusted environments, ParDef offers a unified defense against unpredictable parameter attacks without retraining.
ParDef is a generalized defense against diverse parameter attacks on DNNs, using keyed channel reparameterization, QC-LDPC quantization, and adaptive robust inference. It reduces attack success rates across CIFAR-10, CIFAR-100, and Tiny-ImageNet with moderate overhead.
Deep neural networks are increasingly deployed across heterogeneous and partially untrusted environments, where models are distributed through cloud storage, CI/CD pipelines, containerized services, and edge execution platforms. This broad deployment landscape exposes model parameters to various integrity risks. Unlike input-space adversarial attacks, parameter attacks directly tamper with the model's internal parameters and persist across all subsequent inferences. Existing defenses either require retraining, incur significant accuracy degradation, or are limited to specific attack classes. However, in real-world deployment scenarios, the forms of parameter attacks are often unpredictable. To address this challenge, we present ParDef, a generalized defense for deep neural networks against diverse types of parameter attacks. ParDef integrates keyed channel reparameterization, which obscures sensitive parameter directions, QC-LDPC quantization, which embeds redundancy and supports error correction, and adaptive robust inference, which stabilizes predictions under uncertainty. Our evaluation on CIFAR-10, CIFAR-100, and Tiny-ImageNet using ResNet and VGG models demonstrates that ParDef consistently reduces attack success rates across different parameter attacks while maintaining high model performance and incurring only moderate deployment overhead. These results highlight that ParDef is a practical and generalized defense for DNN deployments.